mirrored 6 minutes ago
0
yuanmengqifeat: standardize configuration fields across all evaluation examples - Add `fixed_ip` field to all 369 JSON files in examples directory - Set to `true` for 8 files listed in google_chrome.json multi_apps - Set to `false` for remaining 361 files - Add `possibility_of_env_change` field to 363 JSON files missing this field - Set to "low" for newly added fields - Preserve existing values (4 medium, 2 high) for 6 files that already had this field This ensures consistent configuration schema across all evaluation examples while maintaining backward compatibility with existing settings. e433f35
{
  "id": "3e3fc409-bff3-4905-bf16-c968eee3f807",
  "snapshot": "chrome",
  "instruction": "I'm a huge movie fan and have kept a record of all the movies I've watched. I'm curious to find out if there are any films released before 2024 from the IMDB Top 30 list that I haven't seen yet. Help me create another sheet 'unseen_movies' in the opened Excel. This sheet should share the same headers and sort the results according to IMDB rankings from high to low.",
  "source": "authors",
  "config": [
    {
      "type": "launch",
      "parameters": {
        "command": [
          "google-chrome",
          "--remote-debugging-port=1337"
        ]
      }
    },
    {
      "type": "launch",
      "parameters": {
        "command": [
          "socat",
          "tcp-listen:9222,fork",
          "tcp:localhost:1337"
        ]
      }
    },
    {
      "type": "chrome_open_tabs",
      "parameters": {
        "urls_to_open": [
          "https://www.imdb.com"
        ]
      }
    },
    {
      "type": "download",
      "parameters": {
        "files": [
          {
            "url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3e3fc409-bff3-4905-bf16-c968eee3f807/movies.xlsx",
            "path": "/home/user/Desktop/movies.xlsx"
          }
        ]
      }
    },
    {
      "type": "launch",
      "parameters": {
        "command": [
          "libreoffice",
          "--calc",
          "/home/user/Desktop/movies.xlsx"
        ]
      }
    }
  ],
  "trajectory": "trajectories/",
  "related_apps": [
    "libreoffice_calc",
    "chrome"
  ],
  "evaluator": {
    "func": "compare_table",
    "result": {
      "type": "vm_file",
      "path": "/home/user/Desktop/movies.xlsx",
      "dest": "movies.xlsx"
    },
    "expected": {
      "type": "cloud_file",
      "path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3e3fc409-bff3-4905-bf16-c968eee3f807/gold_movies.xlsx",
      "dest": "gold_movies.xlsx"
    },
    "options": {
      "rules": [
        {
          "type": "sheet_data",
          "sheet_idx0": "RNunseen_movies",
          "sheet_idx1": "ENunseen_movies"
        }
      ]
    }
  },
  "proxy": true,
  "fixed_ip": false,
  "possibility_of_env_change": "low"
}